Security audit

Canva Skill

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only Canva API helper whose credential use, uploads, exports, and design-management actions match its stated purpose, though users should protect tokens and confirm uploads.

Install only if you want an agent to operate your Canva integration. Keep CANVA_CLIENT_SECRET and ~/.canva/tokens.json private, restrict token-file permissions, grant only the scopes you need, review write or batch actions before running them, and confirm the exact local files before any upload to Canva.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 89% confidence
Finding: The skill instructs users to store Canva OAuth tokens in `~/.canva/tokens.json` but does not warn that these are sensitive bearer credentials or recommend restrictive file permissions. Local token persistence is common, but undocumented storage of reusable access tokens increases the chance of accidental disclosure through backups, shared machines, or permissive filesystem access.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The upload workflow sends a local file directly to Canva without clearly warning that local asset contents and metadata leave the user's environment and are transmitted to a third-party service. This can lead to unintended exfiltration of sensitive images or documents if operators assume the action is purely local.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.